CtrlK
BlogDocsLog inGet started
Tessl Logo

alfworld-receptacle-searcher

This skill searches for a specific receptacle (e.g., garbage can, cabinet) by systematically exploring the environment, checking multiple locations until found. Trigger when the target receptacle is not initially visible, often after scanning nearby areas. It outputs the receptacle's location and may involve navigating through multiple waypoints.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A clear, actionable, well-sequenced search procedure that mostly respects token budget. The main gap is progressive disclosure: relevant bundle files exist on disk but are not linked from SKILL.md, and some trajectory recap could be trimmed.

Suggestions

Add one-level-deep links to the existing bundle files, e.g. '**Environment context**: See [environment_guide.md](references/environment_guide.md)' and '**Search template**: See [search_pattern_template.json](assets/search_pattern_template.json)'.

Trim the redundant trajectory recap (e.g. 'checking 20 cabinets', 'The search pattern in the trajectory was exhaustive') and keep only the transferable heuristic.

Reference the search_pattern_template's 'smart' vs 'exhaustive' strategy in the Core Procedure so the actionable guidance ties to the provided asset.

DimensionReasoningScore

Conciseness

The body is mostly efficient and instruction-focused, but it rehashes trajectory detail ('The trajectory demonstrates checking 20 cabinets', 'The search pattern in the trajectory was exhaustive') that could be tightened.

2 / 3

Actionability

Provides concrete, executable guidance — explicit action formats like 'go to {recep}' and 'put lettuce 1 in/on garbagecan 1' plus a worked example — which is actionable for an instruction-only skill.

3 / 3

Workflow Clarity

A clearly numbered Core Procedure (Identify Target → Initial Check → Systematic Search → Persistence → Output) with an error-handling note ('Nothing happened') and an explicit termination condition ('Continue the search until the target is found').

3 / 3

Progressive Disclosure

Sections are well organized, but the existing bundle files (references/environment_guide.md and assets/search_pattern_template.json) are never referenced or linked from the body, so the available reference/asset layer is not signaled.

2 / 3

Total

10

/

12

Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-constructed description that states concrete actions and gives an explicit trigger clause, answering both what and when clearly. The only weakness is trigger-term breadth, which leans procedural over naturally phrased user keywords.

DimensionReasoningScore

Specificity

Names several concrete actions — 'searches for a specific receptacle', 'systematically exploring the environment', 'checking multiple locations', 'outputs the receptacle's location' — rather than vague language, matching the multi-action anchor.

3 / 3

Completeness

Explicitly answers what ('searches... outputs the receptacle's location') and when via an explicit 'Trigger when the target receptacle is not initially visible' clause.

3 / 3

Trigger Term Quality

Relevant terms appear ('receptacle', 'garbage can', 'cabinet', 'not initially visible', 'scanning nearby areas') but the phrasing is procedural/niche and lacks a broad spread of natural user variations.

2 / 3

Distinctiveness Conflict Risk

Scoped to a clear niche (specific receptacle search with examples like garbage can/cabinet) with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
zjunlp/SkillNet
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.